Training in progress, step 5500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50fd54fc6057e47c4cb3462fc4fbd224afaec0f613a670b5095228721ae3bd42
+oid sha256:8322b5283d76576b6243d188fe146f52a61201fd3c25ceb62074d59997bad9c2
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8192a0952e68fd26a0f0d9493f32bd39f2235e1c44b01851dc5de317b196b387
+oid sha256:5a4cbaa339a503815e8f93b8496d408a46cf594a349bfa6e55b537a7341aed97
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:759bf8b1d224002535229b7cdbc76ddeb1a0d0aa895c4ae5f0ffef98417bab39
+oid sha256:17e30f2d5aa88fa3a0cef0484b7fc130d9829c04f56c17d8644266ef1a1405ee
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7211fac2cf232e2d3daade79b26ee02ede73fbb567f37dbd6997fc9c8b853fd0
+oid sha256:e13ecaded8f565c1efc7f8c1f8e87f707a0c1e13fed3f11510caa036a76b90cf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0390689941812137,
+  "epoch": 1.142975893599335,
   "eval_steps": 500,
-  "global_step": 5000,
+  "global_step": 5500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -85,6 +85,13 @@
       "learning_rate": 1.3077029648101969e-05,
       "loss": 0.4064,
       "step": 5000
+    },
+    {
+      "epoch": 1.142975893599335,
+      "grad_norm": 0.6136273741722107,
+      "learning_rate": 1.2384316985314493e-05,
+      "loss": 0.3599,
+      "step": 5500
     }
   ],
   "logging_steps": 500,
@@ -104,7 +111,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6088969947709440.0,
+  "total_flos": 6697927838269440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null